Visible to the public Biblio

Filters: Keyword is road accidents  [Clear All Filters]
Arthi, A., Aravindhan, K..  2019.  Enhancing the Performance Analysis of LWA Protocol Key Agreement in Vehicular Ad hoc Network. 2019 5th International Conference on Advanced Computing Communication Systems (ICACCS). :1070–1074.

Road accidents are challenging threat in the present scenario. In India there are 5, 01,423 road accidents in 2015. A day 400 hundred deaths are forcing to India to take car safety sincerely. The common cause for road accidents is driver's distraction. In current world the people are dominated by the tablet PC and other hand held devices. The VANET technology is a vehicle-to-vehicle communication; here the main challenge will be to deliver qualified communication during mobility. The paper proposes a standard new restricted lightweight authentication protocol utilizing key agreement theme for VANETs. Inside the planned topic, it has three sorts of validations: 1) V2V 2) V2CH; and 3) CH and RSU. Aside from this authentication, the planned topic conjointly keeps up mystery keys between RSUs for the safe communication. Thorough informal security analysis demonstrates the planned subject is skilled to guard different malicious attack. In addition, the NS2 Simulation exhibits the possibility of the proposed plan in VANET background.

Chowdhury, Abdullahi, Karmakar, Gour, Kamruzzaman, Joarder.  2019.  Trusted Autonomous Vehicle: Measuring Trust using On-Board Unit Data. 2019 18th IEEE International Conference On Trust, Security And Privacy In Computing And Communications/13th IEEE International Conference On Big Data Science And Engineering (TrustCom/BigDataSE). :787—792.

Vehicular Ad-hoc Networks (VANETs) play an essential role in ensuring safe, reliable and faster transportation with the help of an Intelligent Transportation system. The trustworthiness of vehicles in VANETs is extremely important to ensure the authenticity of messages and traffic information transmitted in extremely dynamic topographical conditions where vehicles move at high speed. False or misleading information may cause substantial traffic congestions, road accidents and may even cost lives. Many approaches exist in literature to measure the trustworthiness of GPS data and messages of an Autonomous Vehicle (AV). To the best of our knowledge, they have not considered the trustworthiness of other On-Board Unit (OBU) components of an AV, along with GPS data and transmitted messages, though they have a substantial relevance in overall vehicle trust measurement. In this paper, we introduce a novel model to measure the overall trustworthiness of an AV considering four different OBU components additionally. The performance of the proposed method is evaluated with a traffic simulation model developed by Simulation of Urban Mobility (SUMO) using realistic traffic data and considering different levels of uncertainty.

M.R., Anala, Makker, Malika, Ashok, Aakanksha.  2019.  Anomaly Detection in Surveillance Videos. 2019 26th International Conference on High Performance Computing, Data and Analytics Workshop (HiPCW). :93–98.
Every public or private area today is preferred to be under surveillance to ensure high levels of security. Since the surveillance happens round the clock, data gathered as a result is huge and requires a lot of manual work to go through every second of the recorded videos. This paper presents a system which can detect anomalous behaviors and alarm the user on the type of anomalous behavior. Since there are a myriad of anomalies, the classification of anomalies had to be narrowed down. There are certain anomalies which are generally seen and have a huge impact on public safety, such as explosions, road accidents, assault, shooting, etc. To narrow down the variations, this system can detect explosion, road accidents, shooting, and fighting and even output the frame of their occurrence. The model has been trained with videos belonging to these classes. The dataset used is UCF Crime dataset. Learning patterns from videos requires the learning of both spatial and temporal features. Convolutional Neural Networks (CNN) extract spatial features and Long Short-Term Memory (LSTM) networks learn the sequences. The classification, using an CNN-LSTM model achieves an accuracy of 85%.